JPH03196355A - Parallel computer - Google Patents

Parallel computer

Info

Publication number
JPH03196355A
JPH03196355A JP1337940A JP33794089A JPH03196355A JP H03196355 A JPH03196355 A JP H03196355A JP 1337940 A JP1337940 A JP 1337940A JP 33794089 A JP33794089 A JP 33794089A JP H03196355 A JPH03196355 A JP H03196355A
Authority
JP
Japan
Prior art keywords
substrates
processor
torus network
dummy
parallel computer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP1337940A
Other languages
Japanese (ja)
Inventor
Arisada Takahashi
高橋 有貞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to JP1337940A priority Critical patent/JPH03196355A/en
Publication of JPH03196355A publication Critical patent/JPH03196355A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To compose a torus network of plural processors without altering the wiring of a mother board where substrates are mounted by coupling respective processor substrates mutually through dummy substrates whether a repeating line is arranged. CONSTITUTION:The processor substrates 3... 3 and dummy substrates 5 which are mounted on the unshown mother board are substrates which repeat mutual coupling signals among the processor substrates 3... 3 to realize the torus network. Then lateral processor substrates 3 are coupled mutually with signals, the dummy substrates 5 are mounted between the processor substrates 3 and the dummy substrates 5 repeat the signals among the processor substrates 3. Consequently, the torus network is formed of only the processor substrates mounted currently on the mother board.

Description

【発明の詳細な説明】 (産業上の利用分野〕 この発明は、複数のプロセッサ基板をトーラス網形式で
相互結合し、構成した並列計算機に関するものである。
DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a parallel computer configured by interconnecting a plurality of processor boards in a torus network format.

〔従来の技術〕[Conventional technology]

第2図は複数のプロッサを相互結合するトーラス網を示
す図であり、並列計算機を構成する各プロセッサ(1,
)は、トーラス網方式を採る相互結合網にて各々相互結
合されている・ 第3図は従来のトーラス網実現方式を示す図であり、マ
ザーボード(4)に複数のプロセッサ基板(3)が実装
され、各プロセッサ基板(3)はマザーボード(4)中
で相互結合網にて相互結合される。
FIG. 2 is a diagram showing a torus network that interconnects multiple processors, and shows each processor (1, 1,
) are each interconnected by an interconnection network that adopts a torus network method. Figure 3 is a diagram showing a conventional torus network implementation method, in which multiple processor boards (3) are mounted on a motherboard (4). Each processor board (3) is interconnected in an interconnection network within the motherboard (4).

実際マザーボード(4)には各プロセッサ基板(3)を
相互結合する相互結合網がプリント配線され、該プリン
ト配線によって各プロセッサ基板(3)を相互結合する
ことで第2図に示すトーラス網が実現する。
In fact, an interconnection network is printed on the motherboard (4) that interconnects each processor board (3), and by interconnecting each processor board (3) using the printed wiring, the torus network shown in Figure 2 is realized. do.

(発明が解決しようとする課題〕 従来の並列計算機は、以上のように構成されているため
、トーラス網を構成するプロセッサ数はマザーボードの
配線により固定であり、プロセッサ数を可変する為には
、そのプロセッサ数に応じたトーラス網を実現する必要
がある。
(Problem to be Solved by the Invention) Conventional parallel computers are configured as described above, so the number of processors that make up the torus network is fixed by wiring on the motherboard, and in order to vary the number of processors, It is necessary to realize a torus network corresponding to the number of processors.

この発明は上記のような問題点を解消するためになされ
たもので、マザーボード上のトーラス接続に変更を加え
ることなくプロセッサの数に応じたトーラス網を容易に
実現できる並列計算機を得ることを目的とする。
This invention was made to solve the above-mentioned problems, and the purpose is to obtain a parallel computer that can easily realize a torus network according to the number of processors without changing the torus connection on the motherboard. shall be.

〔課題を解決するための手段〕[Means to solve the problem]

この発明に係る並列計算機は、並列計算機を構成する複
数のプロセッサ用基板とともに、これらプロセッサ用基
板を相互結合する信号線網を配設したダミー基板をマザ
ーボードに立設したものである。
The parallel computer according to the present invention includes a plurality of processor boards constituting the parallel computer, and a dummy board on which a signal line network for interconnecting these processor boards is installed upright on the motherboard.

〔作用〕[Effect]

この発明によれば、マザーボード上て実装されないプロ
セッサ基板の代わりにダミー基板を実装することで、プ
ロセッサ基板間の相互結合信号をダミー基板によって中
継し、トーラス網を実現することができる。
According to this invention, by mounting a dummy board in place of a processor board that is not mounted on a motherboard, mutual coupling signals between processor boards can be relayed by the dummy board, and a torus network can be realized.

〔実施例〕〔Example〕

以下、この発明の一実施例を図について説明する。第1
図は本実施例における並列計算機の構成図である。複数
のプロセッサ基板(3)・・・(3)と図示しないマザ
ーボードに実装されたダミー基板(5)は、各プロセッ
サ基板(3)・・・(3)間の相互結合信号を中継し、
トーラス網を実現する基板である。
An embodiment of the present invention will be described below with reference to the drawings. 1st
The figure is a configuration diagram of a parallel computer in this embodiment. A plurality of processor boards (3)...(3) and a dummy board (5) mounted on a motherboard (not shown) relay mutual coupling signals between each processor board (3)...(3),
This is a board that realizes a torus network.

次に、本実施例の作用について説明する。図に示す横方
向のプロセッサ基板間を信号によって相互結合する場合
は、各プロセッサ基板間にダミー基板を実装し、該ダミ
ー基板により、プロセッサ基板間の信号を中継すること
で、現在マサ−ボードに実装されている数のプロセッサ
基板のみでトーラス網を形成することができる。
Next, the operation of this embodiment will be explained. When interconnecting processor boards in the horizontal direction shown in the figure using signals, a dummy board is mounted between each processor board, and the dummy board relays signals between the processor boards. A torus network can be formed using only the number of processor boards mounted.

又、上記実施例ては横方向のプロセッサ基板間の相互結
合信号を中継する場合を示したが、ダミー基板に配設し
た中継線路によって、各方向のプロセッサ基板間の相互
結合信号を中継することができ、数々のプロセッサ数の
トーラス網を実現することができる。
Further, although the above embodiment shows a case in which mutually coupled signals between processor boards in the horizontal direction are relayed, mutually coupled signals between processor boards in each direction may be relayed by a relay line arranged on a dummy board. It is possible to realize a torus network with a large number of processors.

〔発明の効果〕〔Effect of the invention〕

以上のように、この発明によれば各プロセッサ基板間を
中継線路を配設したり′ミー基板を介して相互結合する
構成としたので、基板を実装するマザーボードの配線を
変更せずとも、数々のプロセッサから構成される並列計
算機が容易かつ安価にできる効果がある。
As described above, according to the present invention, each processor board is configured to be connected to each other via a relay line or a base board, so that it is possible to perform various This has the effect that a parallel computer consisting of several processors can be easily and inexpensively created.

【図面の簡単な説明】[Brief explanation of drawings]

第1図はこの発明の一実施例による並列計算機の構成方
式を示した図、第2図は従来のトーラス網による並列計
算機を示した図、第3図は従来のトーラス網実現方式を
示す図である。 図において、(1)はプロセッサ、(2)は相互結合網
、(3)はプロセッサ基板、(4)はマザーボート、(
5)はダミー基板。 尚、図中同一符号は同−又は相当部分を示す。
FIG. 1 is a diagram showing a configuration method of a parallel computer according to an embodiment of the present invention, FIG. 2 is a diagram showing a parallel computer using a conventional torus network, and FIG. 3 is a diagram showing a conventional torus network implementation method. It is. In the figure, (1) is a processor, (2) is an interconnection network, (3) is a processor board, (4) is a motherboard, (
5) is a dummy board. Note that the same reference numerals in the figures indicate the same or corresponding parts.

Claims (1)

【特許請求の範囲】[Claims] 並列計算機を構成する複数のプロセッサ用基板とともに
、これらプロセッサ用基板を相互結合する信号線網を配
設したダミー基板をマザーボードに立設したことを特徴
とする並列計算機。
1. A parallel computer comprising a plurality of processor boards constituting the parallel computer, and a dummy board on which a signal line network for mutually coupling these processor boards is installed on a motherboard.
JP1337940A 1989-12-26 1989-12-26 Parallel computer Pending JPH03196355A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP1337940A JPH03196355A (en) 1989-12-26 1989-12-26 Parallel computer

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP1337940A JPH03196355A (en) 1989-12-26 1989-12-26 Parallel computer

Publications (1)

Publication Number Publication Date
JPH03196355A true JPH03196355A (en) 1991-08-27

Family

ID=18313433

Family Applications (1)

Application Number Title Priority Date Filing Date
JP1337940A Pending JPH03196355A (en) 1989-12-26 1989-12-26 Parallel computer

Country Status (1)

Country Link
JP (1) JPH03196355A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015027320A1 (en) 2013-08-29 2015-03-05 Dan Oprea Method and apparatus to manage the direct interconnect switch wiring and growth in computer networks

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015027320A1 (en) 2013-08-29 2015-03-05 Dan Oprea Method and apparatus to manage the direct interconnect switch wiring and growth in computer networks
JP2016532209A (en) * 2013-08-29 2016-10-13 ダン オプレア Method and apparatus for managing the wiring and growth of direct interconnect switches in a computer network
EP3022879A4 (en) * 2013-08-29 2017-03-01 Dan Oprea Method and apparatus to manage the direct interconnect switch wiring and growth in computer networks
AU2014311217B2 (en) * 2013-08-29 2018-02-08 Rockport Networks Inc. Method and apparatus to manage the direct interconnect switch wiring and growth in computer networks
US10303640B2 (en) 2013-08-29 2019-05-28 Rockport Networks Inc. Method and apparatus to manage the direct interconnect switch wiring and growth in computer networks
AU2018200155B2 (en) * 2013-08-29 2019-09-26 Rockport Networks Inc. Method And Apparatus To Manage The Direct Interconnect Switch Wiring And Growth In Computer Networks

Similar Documents

Publication Publication Date Title
US4942550A (en) Printed circuit board topography for high speed intelligent industrial controller with multiple boards located within a single slot
JPH06290157A (en) Net
JPH03196355A (en) Parallel computer
JPH11316733A (en) Data processor
JPH04107717A (en) Electromagnetically coupled computer module device and computer device using the same
JPH117348A (en) Multi-processor connection system
JPH02196499A (en) Unit structure for printed board having double rear wiring board
JPH07221420A (en) Interconnection between ic-mounted printed circuit board
JPH0337223B2 (en)
JP2877358B2 (en) Multistage connection switch network
JPH0210890A (en) High density mounting structure for integrated circuit
JPS61166667A (en) Multi-processor system
JPH04156608A (en) Radial bus
JPH04276698A (en) Common bus separate type back wiring board
JPS60105057A (en) Test system
JPS62211764A (en) Inter-circuit connection structure
JPS63114434A (en) Distributed small-sized terminal equipment
JP2000013015A (en) Printed board
JPH11305874A (en) Base board and electronic equipment
JPH1197808A (en) Circuit board
JPH10294538A (en) Wiring board structure
JPH0438155B2 (en)
JPS61228519A (en) Bus formation system
JPH03237566A (en) Balanced transmission wiring information forming system
JP2002352882A (en) Mounting method for surface mount connector